Imagen de Portada

ToSA: Token Selective Attention for Efficient Vision Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Singh, Manish Kumar, Yasarla, Rajeev, Cai, Hong, Lee, Mingu, Porikli, Fatih
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
por: Yasarla, Rajeev, et al.
Publicado: (2025)

MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation
por: Yasarla, Rajeev, et al.
Publicado: (2023)

DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions
por: Shi, Yunxiao, et al.
Publicado: (2024)

ToSA: Token Merging with Spatial Awareness
por: Huang, Hsiang-Wei, et al.
Publicado: (2025)

FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
por: Yasarla, Rajeev, et al.
Publicado: (2024)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
por: Letourneau, Pierre-David, et al.
Publicado: (2024)

HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation
por: Mercier, Antoine, et al.
Publicado: (2024)

CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers
por: Li, Zhuojin, et al.
Publicado: (2026)

Do-Undo Bench: Reversibility for Action Understanding in Image Generation
por: Mahajan, Shweta, et al.
Publicado: (2025)

RoCA: Robust Cross-Domain End-to-End Autonomous Driving
por: Yasarla, Rajeev, et al.
Publicado: (2025)

H3O: Hyper-Efficient 3D Occupancy Prediction with Heterogeneous Supervision
por: Shi, Yunxiao, et al.
Publicado: (2025)

Distilling Multi-modal Large Language Models for Autonomous Driving
por: Hegde, Deepti, et al.
Publicado: (2025)

HAViT: Historical Attention Vision Transformer
por: Banik, Swarnendu, et al.
Publicado: (2026)

Attention Guided Alignment in Efficient Vision-Language Models
por: Mahajan, Shweta, et al.
Publicado: (2025)

MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
por: Yasarla, Rajeev, et al.
Publicado: (2026)

Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties
por: Jeong, Jisoo, et al.
Publicado: (2025)

Generative Scenario Rollouts for End-to-End Autonomous Driving
por: Yasarla, Rajeev, et al.
Publicado: (2026)

FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
por: Cho, Janghoon, et al.
Publicado: (2025)

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
por: Lee, Sanghyeok, et al.
Publicado: (2024)

Planar Gaussian Splatting
por: Zanjani, Farhad G., et al.
Publicado: (2024)

Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding
por: Zanjani, Farhad G., et al.
Publicado: (2024)

CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
por: Lee, Jungsoo, et al.
Publicado: (2025)

Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
por: Lee, Dong Hoon, et al.
Publicado: (2024)

Learning Optical Flow Field via Neural Ordinary Differential Equation
por: Mirvakhabova, Leyla, et al.
Publicado: (2025)

SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations
por: Lin, Jamie Menjay, et al.
Publicado: (2024)

OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation
por: Jeong, Jisoo, et al.
Publicado: (2024)

FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices
por: Han, Shizhong, et al.
Publicado: (2025)

HEART-VIT: Hessian-Guided Efficient Dynamic Attention and Token Pruning in Vision Transformer
por: Uddin, Mohammad Helal, et al.
Publicado: (2025)

TCSAFormer: Efficient Vision Transformer with Token Compression and Sparse Attention for Medical Image Segmentation
por: Xia, Zunhui, et al.
Publicado: (2025)

BePo: Dual Representation for 3D Occupancy Prediction
por: Shi, Yunxiao, et al.
Publicado: (2025)

ODG: Occupancy Prediction Using Dual Gaussians
por: Shi, Yunxiao, et al.
Publicado: (2025)

Segmentation-Free Guidance for Text-to-Image Diffusion Models
por: Azarian, Kambiz, et al.
Publicado: (2024)

Resolving the Identity Crisis in Text-to-Image Generation
por: Borse, Shubhankar, et al.
Publicado: (2025)

LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation
por: Farhadzadeh, Farzad, et al.
Publicado: (2025)

Speed-up of Vision Transformer Models by Attention-aware Token Filtering
por: Naruko, Takahiro, et al.
Publicado: (2025)

Context-Aware Token Selection and Packing for Enhanced Vision Transformer
por: Zhang, Tianyi, et al.
Publicado: (2024)

PPT: Token Pruning and Pooling for Efficient Vision Transformers
por: Wu, Xinjian, et al.
Publicado: (2023)

Context-Aware Token Pruning and Discriminative Selective Attention for Transformer Tracking
por: Kugarajeevan, Janani, et al.
Publicado: (2025)

Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens
por: Lew, Jaihyun, et al.
Publicado: (2024)

Frequency-Aware Token Reduction for Efficient Vision Transformer
por: Lee, Dong-Jae, et al.
Publicado: (2025)